An Improved Indoor Location Algorithm for WiFi Position Fingerprint Based on IABC-KMC

The location fingerprint location algorithm based on RSSI has become one of the main technical solutions for indoor location because of its low cost and easy layout. To improve the positioning accuracy and stability, an improved WKNN positioning algorithm is proposed. The algorithm uses wavelet de-noising to process the original data in the off-line stage, Then the improved artificial bee colony (IABC) is used to optimize K-means clustering (IABC-KMC) to avoid the problem that the traditional K-means clustering (KMC) algorithm falls into the local optimal solution. The fingerprint data is partitioned and an offline fingerprint database is established, In the online stage, according to the data collected by the points to be measured, the WKNN algorithm is used to match with the fingerprint database. Because of the problem that RSSI European distance is close but the physical distance is far when using European distance calculation, the DPC algorithm is proposed to calculate the decision value of k nearest neighbor points and determine the weight of the coordinates of the nearest neighbor points through the decision value, to calculate the actual position of the points to be measured. To solve the problem of location accuracy degradation caused by only using a single cluster when the points to be measured are located at the cluster boundary of the fingerprint database, an adaptive location cluster selection method based on the Euclidean distance between the points to be measured and the centers of various clusters is proposed. The experimental results show that the average positioning error of the proposed algorithm is less than the traditional algorithm, such as KNN, WKNN and IABC-WKNN.